📊 数据分析技术在线学习

# 模拟NumPy的简单实现 class np: @staticmethod def array(data): return data @staticmethod def sum(arr): return sum(arr) @staticmethod mean(arr): return sum(arr) / len(arr) # 创建数组 scores = [85, 92, 78, 95, 88] print(f"成绩数组：{scores}") print(f"总分：{np.sum(scores)}") print(f"平均分：{np.mean(scores):.1f}") print(f"最高分：{max(scores)}") print(f"最低分：{min(scores)}")

# 模拟DataFrame data = { "姓名": ["张三", "李四", "王五", "赵六"], "语文": [85, 92, 78, 88], "数学": [90, 85, 95, 82], "英语": [88, 90, 82, 91] } print("="*40) print("学生成绩表") print("="*40) for i, name in enumerate(data["姓名"]): print(f"{name}: 语文{data['语文'][i]}, 数学{data['数学'][i]}, 英语{data['英语'][i]}") print("="*40) # 计算每科平均分 avg_chinese = sum(data["语文"]) / len(data["语文"]) avg_math = sum(data["数学"]) / len(data["数学"]) avg_english = sum(data["英语"]) / len(data["英语"]) print(f"平均分: 语文{avg_chinese:.1f}, 数学{avg_math:.1f}, 英语{avg_english:.1f}")

# 学生成绩数据 students = [ {"姓名": "张三", "成绩": 85}, {"姓名": "李四", "成绩": 92}, {"姓名": "王五", "成绩": 78}, {"姓名": "赵六", "成绩": 95} ] print("所有学生：") for s in students: print(f" {s['姓名']}: {s['成绩']}分") # 筛选成绩 >= 90 的学生 print("\n成绩 >= 90 分的学生：") high_scores = [s for s in students if s["成绩"] >= 90] for s in high_scores: print(f" {s['姓名']}: {s['成绩']}分") # 筛选成绩 80-90 之间的学生 print("\n成绩 80-90 分之间的学生：") mid_scores = [s for s in students if 80 <= s["成绩"] < 90] for s in mid_scores: print(f" {s['姓名']}: {s['成绩']}分")

# 模拟数据清洗操作 raw_data = [85, None, 78, 92, None, 88] print(f"原始数据：{raw_data}") print(f"缺失值数量：{raw_data.count(None)}") # 处理缺失值（用平均值填充） valid_nums = [x for x raw_data if x is not None] avg = sum(valid_nums) / len(valid_nums) cleaned_data = [avg if x is None else x for x raw_data] print(f"平均值：{avg:.1f}") print(f"清洗后数据：{[round(x, 1) for x in cleaned_data]}") # 去除重复 with_duplicates = [1, 2, 2, 3, 3, 3] unique = list(set(with_duplicates)) print(f"去重前：{with_duplicates}") print(f"去重后：{sorted(unique)}")

import math # 销售数据 sales = [120, 150, 130, 180, 160, 140, 170, 155] print("="*40) print("销售数据统计分析") print("="*40) print(f"数据：{sales}") print(f"数量：{len(sales)}") # 计算统计量 n = len(sales) total = sum(sales) mean = total / n sorted_sales = sorted(sales) median = (sorted_sales[n//2-1] + sorted_sales[n//2]) / 2 if n % 2 == 0 else sorted_sales[n//2] # 计算标准差 variance = sum((x - mean)**2 for x in sales) / n std = math.sqrt(variance) print(f"总和：{total}") print(f"平均值：{mean:.2f}") print(f"中位数：{median:.2f}") print(f"最大值：{max(sales)}") print(f"最小值：{min(sales)}") print(f"标准差：{std:.2f}")

# 模拟数据合并操作 # 表1：学生信息 students = { "学号": ["001", "002", "003"], "姓名": ["张三", "李四", "王五"] } # 表2：成绩信息 scores = { "学号": ["001", "002", "003"], "成绩": [85, 92, 78] } print("学生信息表：") for i in range(len(students["学号"])): print(f" {students['学号'][i]}: {students['姓名'][i]}") print("\n成绩表：") for i in range(len(scores["学号"])): print(f" {scores['学号'][i]}: {scores['成绩'][i]}分") # 基于学号合并数据 print("\n合并后的数据表：") for i in range(len(students["学号"])): student_id = students["学号"][i] if student_id in scores["学号"]: idx = scores["学号"].index(student_id) score = scores["成绩"][idx] print(f" {student_id} | {students['姓名'][i]} | {score}分")

# 模拟数据可视化（文本图表） # 月度销售额数据 months = ["1月", "2月", "3月", "4月", "5月"] sales = [120, 150, 130, 180, 200] print("="*50) print("月度销售额柱状图（文本版）") print("="*50) print("单位：万元") print() for i, month in enumerate(months): bar = "█" * (sales[i] // 10) print(f"{month:4} | {bar:20} {sales[i]}") print() print("="*50) print("销售额趋势分析") print("="*50) max_sale = max(sales) min_sale = min(sales) max_month = months[sales.index(max_sale)] min_month = months[sales.index(min_sale)] print(f"最高销售额：{max_sale}万元 ({max_month})") print(f"最低销售额：{min_sale}万元 ({min_month})") print(f"总销售额：{sum(sales)}万元")